© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 4765
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Hentet
    -0.65
    ligente
    -0.55
     disambiguazione
    -0.53
    ToTensor
    -0.52
     opérés
    -0.52
    OneToOne
    -0.52
     very
    -0.51
     defaultstate
    -0.50
     olyan
    -0.50
     plutôt
    -0.49
    POSITIVE LOGITS
    importance
    0.72
     similarities
    0.71
     significance
    0.70
    LookAnd
    0.68
     importance
    0.66
    ✨:
    0.65
     Importance
    0.64
     Significance
    0.62
    Importance
    0.62
     meanings
    0.60
    Activations Density 0.015%

    No Known Activations